VibeVoice ASR Streaming
Transcribe authorized WAV files locally with the 1.5B streaming checkpoint. Native speaker-prefixed text and complete chunk outputs arrive progressively; hotword context is optional.
Desktop app
Run VibeVoice ASR Streaming on your computer
Download the desktop app to load this model, provide input and view results locally.
Public desktop downloads are coming soon.Device requirements
If your device falls short
MemoryAdvisory only: close other apps, reduce image/tile/token/batch settings or choose a smaller verified model/precision. CPU can need more RAM than GPU.
GPUIf the selected GPU runtime fails, existing CPU fallback may recover when enabled, but CPU has its own memory/runtime needs.
PlatformUse a compatible OS/architecture/runtime or another model. These estimates do not add hardware detection or block runs.
Benchmark evidence
Saved desktop measurements apply to the recorded hardware and runtime. Fallback cases report the device that actually ran; they do not prove GPU support on the requested device.
VibeVoice ASR Streaming · 1.5B
55 configurations testedQuality criteria
No explicit quality gate recorded. Review per-case evidence; full certification is pending.
| Precision | Device | Result | Platform | Inference / load | Task metric | |
|---|---|---|---|---|---|---|
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1724 ms / 0 ms | 0.164 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1735 ms / 0 ms | 0.165 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1738 ms / 0 ms | 0.165 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1756 ms / 0 ms | 0.167 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1766 ms / 0 ms | 0.167 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1762 ms / 0 ms | 0.168 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1782 ms / 0 ms | 0.171 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1809 ms / 0 ms | 0.173 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1818 ms / 0 ms | 0.173 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 1834 ms / 0 ms | 0.175 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 6619 ms / 3212 ms | 0.189 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 6774 ms / 3558 ms | 0.193 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2058 ms / 3211 ms | 0.195 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2062 ms / 3410 ms | 0.195 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2063 ms / 3237 ms | 0.196 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2077 ms / 3194 ms | 0.197 RTF |
BF16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 344 ms / 0 ms | 0.200 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2157 ms / 0 ms | 0.203 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2157 ms / 0 ms | 0.204 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2170 ms / 0 ms | 0.204 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2182 ms / 0 ms | 0.206 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2287 ms / 0 ms | 0.216 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 373 ms / 0 ms | 0.220 RTF |
FP16 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2339 ms / 3510 ms | 0.222 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2463 ms / 3656 ms | 0.232 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 8189 ms / 3640 ms | 0.232 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 2493 ms / 3713 ms | 0.235 RTF |
FP32 | mpsAccelerated | Passed | Fast | macos · aarch64 | 417 ms / 0 ms | 0.241 RTF |
FP16 | mpsAccelerated | Passed | Moderate | macos · aarch64 | 833 ms / 0 ms | 0.262 RTF |
BF16 | mpsAccelerated | Passed | Moderate | macos · aarch64 | 846 ms / 0 ms | 0.267 RTF |
FP32 | mpsAccelerated | Passed | Moderate | macos · aarch64 | 1097 ms / 0 ms | 0.342 RTF |
BF16 | mpsAccelerated | Passed | Moderate | macos · aarch64 | 3826 ms / 3131 ms | 0.357 RTF |
FP32 | mpsAccelerated | Passed | Moderate | macos · aarch64 | 3987 ms / 4345 ms | 0.372 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6031 ms / 0 ms | 0.556 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6139 ms / 0 ms | 0.566 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6201 ms / 0 ms | 0.571 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6235 ms / 0 ms | 0.574 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6281 ms / 0 ms | 0.579 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6447 ms / 3424 ms | 0.594 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 21199 ms / 10084 ms | 0.597 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6526 ms / 3499 ms | 0.602 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 6566 ms / 3522 ms | 0.606 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7688 ms / 2924 ms | 0.708 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7740 ms / 0 ms | 0.712 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7758 ms / 0 ms | 0.713 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7837 ms / 0 ms | 0.720 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7836 ms / 2845 ms | 0.721 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 7858 ms / 0 ms | 0.722 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 8008 ms / 2677 ms | 0.736 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 8021 ms / 0 ms | 0.737 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 1383 ms / 0 ms | 0.740 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 26995 ms / 2960 ms | 0.760 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 1715 ms / 0 ms | 0.887 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 3075 ms / 0 ms | 0.921 RTF |
FP32 | cpu | Passed | Moderate | macos · aarch64 | 3734 ms / 0 ms | 1.118 RTF |
Test setup & sample details
- Quality gate
- No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
- Tested
- 2026-11-03T00:06:54.156445+00:00
- Environment
- { "os": "macos", "arch": "aarch64", "hardware": "Apple M3 Max", "osVersion": "27.2", "runtime": "Reviewed Microsoft16fb2cb ASR / Transformers4.57.6 / Torch2.10.0", "interpreter": "App-ownedCPython3.13.18 private development venv; packaged managed provisioning tested separately" }
- Runtime
- vibevoice-asr 1.0.0+16fb2cb
- Artifact revision
- 4262d23d8a539a6530cf64fbd0b1751ef9a30853
- Fixture
{ "file": "model-samples/desktop/granite-speech5/granite-speech5-jfk.wav", "size": 3880888, "sha1": "6fb9dfd0ec18bb61a6af995c0df0cd32ee2afe34", "sha256": "c72e27f68334ae37e037ef819fa5aa1fc1552aa840b93e308df4ffe52317bedb", "url": "https://assets.localai.tools/samples/v1/files/c72e27f68334ae37e037ef819fa5aa1fc1552aa840b93e308df4ffe52317bedb/granite-speech5-jfk.wav" }- Rerun when
- Exact checkpoint/tokenizer/preprocessor/reviewed runtime/framework/torch dependency changes; Accepted input decode/resample, chunking/KV/greedy generation or native output changes; Fixture/reference or speech projection/quality/performance gate changes; Relevant OS/backend behavior
Per-case quality & failure details
[
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3499.407583993161,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6622.400374995777,
"inferenceMs": 6525.607500021579,
"firstChunkMs": 2363.594374997774,
"audioSeconds": 11,
"realTimeFactor": 0.6020363977268889,
"audioSecondsPerSecond": 1.6856668133907264,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 10121.807958988938,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " The quick brown fox jumps over the lazy dog."
},
"plainTranscript": "The quick brown fox jumps over the lazy dog.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 3131.3904999988154,
"inferenceMs": 3074.5081669883803,
"firstChunkMs": 2145.2156669984106,
"audioSeconds": 3.4,
"realTimeFactor": 0.9209972058820045,
"audioSecondsPerSecond": 1.1058679357259453,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 2,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 3131.3904999988154,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 0,
"expectedSpeakerCount": 0,
"speakerContent": {},
"plainTranscript": "",
"maximumConsecutiveRepeatedWords": 0,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1479.1136660205666,
"inferenceMs": 1383.3208339929115,
"firstChunkMs": 1479.1130000085104,
"audioSeconds": 2,
"realTimeFactor": 0.7395568330102833,
"audioSecondsPerSecond": 1.44579619626422,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 1,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 1479.1136660205666,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6114.938666985836,
"inferenceMs": 6031.323914969107,
"firstChunkMs": 1972.0030419994146,
"audioSeconds": 11,
"realTimeFactor": 0.5559035151805305,
"audioSecondsPerSecond": 1.8238118454721302,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 6114.938666985836,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6370.299333008006,
"inferenceMs": 6280.85429102066,
"firstChunkMs": 2075.988166994648,
"audioSeconds": 11,
"realTimeFactor": 0.579118121182546,
"audioSecondsPerSecond": 1.7513541136794089,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 6370.299333008006,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6279.902915994171,
"inferenceMs": 6201.450332009699,
"firstChunkMs": 2008.9117079915013,
"audioSeconds": 11,
"realTimeFactor": 0.5709002650903792,
"audioSecondsPerSecond": 1.7737786180793678,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 6279.902915994171,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6230.100917018717,
"inferenceMs": 6139.218623022316,
"firstChunkMs": 2074.0997090179008,
"audioSeconds": 11,
"realTimeFactor": 0.5663728106380652,
"audioSecondsPerSecond": 1.791758964039749,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 6230.100917018717,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6316.436500026612,
"inferenceMs": 6234.626377030509,
"firstChunkMs": 2003.696083003888,
"audioSeconds": 11,
"realTimeFactor": 0.5742215000024192,
"audioSecondsPerSecond": 1.7643398873950153,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 6316.436500026612,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12870434816,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3424.4031660200562,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6539.159666019259,
"inferenceMs": 6447.085124993464,
"firstChunkMs": 2167.328791023465,
"audioSeconds": 11,
"realTimeFactor": 0.5944690605472054,
"audioSecondsPerSecond": 1.7061974189477065,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 9963.562832039315,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12051922944,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3521.8859169981442,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6661.469334008871,
"inferenceMs": 6566.130625928054,
"firstChunkMs": 2288.180042000022,
"audioSeconds": 11,
"realTimeFactor": 0.6055881212735337,
"audioSecondsPerSecond": 1.6752636562793426,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 10183.355251007015,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12702449664,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 2845.3226670098957,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7935.76849999954,
"inferenceMs": 7835.537834063871,
"firstChunkMs": 2558.038040995598,
"audioSeconds": 11,
"realTimeFactor": 0.7214334999999582,
"audioSecondsPerSecond": 1.403860236904107,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 10781.091167009436,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " The quick brown fox jumps over the lazy dog."
},
"plainTranscript": "The quick brown fox jumps over the lazy dog.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 3801.03745800443,
"inferenceMs": 3733.815499028424,
"firstChunkMs": 2508.5268749971874,
"audioSeconds": 3.4,
"realTimeFactor": 1.1179521935307146,
"audioSecondsPerSecond": 0.9105966807638766,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 2,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 3801.03745800443,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 0,
"expectedSpeakerCount": 0,
"speakerContent": {},
"plainTranscript": "",
"maximumConsecutiveRepeatedWords": 0,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1773.669999995036,
"inferenceMs": 1714.5925830118358,
"firstChunkMs": 1773.669415997574,
"audioSeconds": 2,
"realTimeFactor": 0.886834999997518,
"audioSecondsPerSecond": 1.1664578628275766,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 1,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 1773.669999995036,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7842.068499972811,
"inferenceMs": 7757.6913320226595,
"firstChunkMs": 2399.2004999890924,
"audioSeconds": 11,
"realTimeFactor": 0.7129153181793465,
"audioSecondsPerSecond": 1.417947625035498,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 7842.068499972811,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 8110.002375004115,
"inferenceMs": 8021.4134179695975,
"firstChunkMs": 2366.461750003509,
"audioSeconds": 11,
"realTimeFactor": 0.7372729431821923,
"audioSecondsPerSecond": 1.371329393814532,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 8110.002375004115,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7946.097791980719,
"inferenceMs": 7857.703332992969,
"firstChunkMs": 2577.6626669976395,
"audioSeconds": 11,
"realTimeFactor": 0.7223725265437018,
"audioSecondsPerSecond": 1.3999001405172855,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 7946.097791980719,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7923.858249996556,
"inferenceMs": 7837.128582003061,
"firstChunkMs": 2457.5449169788044,
"audioSeconds": 11,
"realTimeFactor": 0.720350749999687,
"audioSecondsPerSecond": 1.4035752871606648,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 7923.858249996556,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7827.346417005174,
"inferenceMs": 7739.859749999596,
"firstChunkMs": 2502.3630829819012,
"audioSeconds": 11,
"realTimeFactor": 0.7115769470004704,
"audioSecondsPerSecond": 1.4212143831159956,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 7827.346417005174,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12271616000,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 2924.03633298818,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 7782.563707994996,
"inferenceMs": 7687.873791961465,
"firstChunkMs": 2639.6545419993345,
"audioSeconds": 11,
"realTimeFactor": 0.7075057916359087,
"audioSecondsPerSecond": 1.4308247374588452,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 10706.600040983176,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12051972096,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 2676.9912090094294,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 8098.800209001638,
"inferenceMs": 8007.557833014289,
"firstChunkMs": 2497.1548750181682,
"audioSeconds": 11,
"realTimeFactor": 0.7362545644546944,
"audioSecondsPerSecond": 1.3737022234979306,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 10775.791418011067,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12046172160,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3409.955750015797,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2150.230042025214,
"inferenceMs": 2061.5820820094086,
"firstChunkMs": 958.1357920251321,
"audioSeconds": 11,
"realTimeFactor": 0.19547545836592856,
"audioSecondsPerSecond": 5.335707996296894,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574049792,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 5560.185792041011,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " The quick brown fox jumps over the lazy dog."
},
"plainTranscript": "The quick brown fox jumps over the lazy dog.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 891.4839579956606,
"inferenceMs": 832.5938750058413,
"firstChunkMs": 683.3275000099093,
"audioSeconds": 3.4,
"realTimeFactor": 0.2622011641163708,
"audioSecondsPerSecond": 4.083623603375831,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 2,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574361088,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 891.4839579956606,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 0,
"expectedSpeakerCount": 0,
"speakerContent": {},
"plainTranscript": "",
"maximumConsecutiveRepeatedWords": 0,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 439.8299169843085,
"inferenceMs": 372.8274169843644,
"firstChunkMs": 439.8286669747904,
"audioSeconds": 2,
"realTimeFactor": 0.21991495849215426,
"audioSecondsPerSecond": 5.364412349759878,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 1,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 439.8299169843085,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1922.1749159914907,
"inferenceMs": 1834.18000000529,
"firstChunkMs": 728.114875004394,
"audioSeconds": 11,
"realTimeFactor": 0.1747431741810446,
"audioSecondsPerSecond": 5.997230369957297,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1922.1749159914907,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1902.8923330188263,
"inferenceMs": 1817.8275410027709,
"firstChunkMs": 707.7809160109609,
"audioSeconds": 11,
"realTimeFactor": 0.17299021209262058,
"audioSecondsPerSecond": 6.051179087061281,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1902.8923330188263,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1819.4328749959823,
"inferenceMs": 1737.9111670306884,
"firstChunkMs": 677.3104160092771,
"audioSeconds": 11,
"realTimeFactor": 0.1654029886359984,
"audioSecondsPerSecond": 6.329437435397847,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1819.4328749959823,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1900.7825409935322,
"inferenceMs": 1809.0135830279905,
"firstChunkMs": 724.4135410001036,
"audioSeconds": 11,
"realTimeFactor": 0.17279841281759384,
"audioSecondsPerSecond": 6.0806619160856785,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1900.7825409935322,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1844.1454999847338,
"inferenceMs": 1762.4733739648946,
"firstChunkMs": 686.4049159921706,
"audioSeconds": 11,
"realTimeFactor": 0.16764959090770307,
"audioSecondsPerSecond": 6.2412290378345885,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651660800,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1844.1454999847338,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098564608,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3210.933416004991,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2146.728209016146,
"inferenceMs": 2057.923541025957,
"firstChunkMs": 959.2745000263676,
"audioSeconds": 11,
"realTimeFactor": 0.19515710991055873,
"audioSecondsPerSecond": 5.3451937259612965,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574049792,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 5357.661625021137,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 6655852544,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3510.1135000004433,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2440.0024579954334,
"inferenceMs": 2338.6723330477253,
"firstChunkMs": 1060.9730830183253,
"audioSeconds": 11,
"realTimeFactor": 0.2218184052723121,
"audioSecondsPerSecond": 4.703523381432812,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574049792,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 5950.115957995877,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 7098253312,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 4344.67200000654,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 4087.297791003948,
"inferenceMs": 3986.885500024073,
"firstChunkMs": 2517.715666006552,
"audioSeconds": 11,
"realTimeFactor": 0.37157252645490435,
"audioSecondsPerSecond": 2.759045876771124,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 10961682432,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 8431.969791010488,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " The quick brown fox jumps over the lazy dog."
},
"plainTranscript": "The quick brown fox jumps over the lazy dog.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1163.1682500010356,
"inferenceMs": 1096.7590420041233,
"firstChunkMs": 922.5431670201942,
"audioSeconds": 3.4,
"realTimeFactor": 0.34210830882383403,
"audioSecondsPerSecond": 3.1000428259858537,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 2,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 10961993728,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1163.1682500010356,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 0,
"expectedSpeakerCount": 0,
"speakerContent": {},
"plainTranscript": "",
"maximumConsecutiveRepeatedWords": 0,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 482.7854579780251,
"inferenceMs": 416.6835419891868,
"firstChunkMs": 482.78429100173526,
"audioSeconds": 2,
"realTimeFactor": 0.24139272898901254,
"audioSecondsPerSecond": 4.799805604157751,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 1,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 482.7854579780251,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2373.4093329985626,
"inferenceMs": 2286.779748945264,
"firstChunkMs": 839.7549579967745,
"audioSeconds": 11,
"realTimeFactor": 0.21576448481805113,
"audioSecondsPerSecond": 4.810257745667702,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 2373.4093329985626,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2241.505000012694,
"inferenceMs": 2157.112207933096,
"firstChunkMs": 841.7572500184178,
"audioSeconds": 11,
"realTimeFactor": 0.20377318181933582,
"audioSecondsPerSecond": 5.099410202003349,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 2241.505000012694,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2260.829917009687,
"inferenceMs": 2182.2794989857357,
"firstChunkMs": 809.7590419929475,
"audioSeconds": 11,
"realTimeFactor": 0.2055299924554261,
"audioSecondsPerSecond": 5.040600896957746,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 2260.829917009687,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2247.5597089796793,
"inferenceMs": 2170.0982919428498,
"firstChunkMs": 816.5612089796923,
"audioSeconds": 11,
"realTimeFactor": 0.20432360990724358,
"audioSecondsPerSecond": 5.068894824184161,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 2247.5597089796793,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2235.3540000040084,
"inferenceMs": 2156.637709995266,
"firstChunkMs": 815.4602500144392,
"audioSeconds": 11,
"realTimeFactor": 0.2032140000003644,
"audioSecondsPerSecond": 5.10053216125213,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11014127616,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 2235.3540000040084,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760779264,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3713.4132500214037,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2584.176165983081,
"inferenceMs": 2493.4970840113238,
"firstChunkMs": 1146.0584579908755,
"audioSeconds": 11,
"realTimeFactor": 0.2349251059984619,
"audioSecondsPerSecond": 4.411474980473667,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 10961682432,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 6297.5894160044845,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11760156672,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3655.770457990002,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2553.0080830212682,
"inferenceMs": 2462.8444999980275,
"firstChunkMs": 1130.6270000059158,
"audioSeconds": 11,
"realTimeFactor": 0.23209164391102438,
"audioSecondsPerSecond": 4.466380236352238,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 10961682432,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 6208.77854101127,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 11806031872,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3130.51658400218,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 3927.2335419955198,
"inferenceMs": 3826.493749016663,
"firstChunkMs": 2709.327124990523,
"audioSeconds": 11,
"realTimeFactor": 0.3570212310905018,
"audioSecondsPerSecond": 2.874694360294406,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574656000,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 7057.7501259977,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " The quick brown fox jumps over the lazy dog."
},
"plainTranscript": "The quick brown fox jumps over the lazy dog.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 909.1722090088297,
"inferenceMs": 846.4546249888372,
"firstChunkMs": 704.0809169993736,
"audioSeconds": 3.4,
"realTimeFactor": 0.2674035908849499,
"audioSecondsPerSecond": 4.016753999122916,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 2,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574967296,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 909.1722090088297,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 0,
"expectedSpeakerCount": 0,
"speakerContent": {},
"plainTranscript": "",
"maximumConsecutiveRepeatedWords": 0,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 400.5893749999814,
"inferenceMs": 344.07399996416643,
"firstChunkMs": 400.5887089879252,
"audioSeconds": 2,
"realTimeFactor": 0.2002946874999907,
"audioSecondsPerSecond": 5.812703081919267,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 1,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 400.5893749999814,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1819.0675410151016,
"inferenceMs": 1734.7158330085222,
"firstChunkMs": 689.7470000258181,
"audioSeconds": 11,
"realTimeFactor": 0.16536977645591833,
"audioSecondsPerSecond": 6.3410962133911415,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1819.0675410151016,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1799.9294580076821,
"inferenceMs": 1723.7946239474695,
"firstChunkMs": 668.3869170083199,
"audioSeconds": 11,
"realTimeFactor": 0.1636299507279711,
"audioSecondsPerSecond": 6.381270626549542,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1799.9294580076821,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1833.2953749923036,
"inferenceMs": 1755.5740000098012,
"firstChunkMs": 671.6254999919329,
"audioSeconds": 11,
"realTimeFactor": 0.16666321590839123,
"audioSecondsPerSecond": 6.265756954670431,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1833.2953749923036,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1882.5023329991382,
"inferenceMs": 1781.9757899851538,
"firstChunkMs": 723.7510829872917,
"audioSeconds": 11,
"realTimeFactor": 0.17113657572719437,
"audioSecondsPerSecond": 6.172923370688243,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1882.5023329991382,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 0,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 1842.1950420015492,
"inferenceMs": 1766.086042043753,
"firstChunkMs": 668.2899169973098,
"audioSeconds": 11,
"realTimeFactor": 0.16747227654559538,
"audioSecondsPerSecond": 6.228462112338854,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5652267008,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 1842.1950420015492,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 1007566848,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3193.998750008177,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2169.038250023732,
"inferenceMs": 2076.778582006227,
"firstChunkMs": 980.6940830021631,
"audioSeconds": 11,
"realTimeFactor": 0.1971852954567029,
"audioSecondsPerSecond": 5.296664793881727,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574656000,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 5363.037000031909,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 759742464,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0,
"maximumWordErrorRate": 0.25,
"speakerCount": 1,
"expectedSpeakerCount": 1,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country."
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": null,
"maximumSpeakerWer": null,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3237.1377919916995,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 2152.8967500198632,
"inferenceMs": 2062.7928740286734,
"firstChunkMs": 965.7093750138301,
"audioSeconds": 11,
"realTimeFactor": 0.1957178863654421,
"audioSecondsPerSecond": 5.332576110037064,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 4,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5574656000,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 5390.034542011563,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 761151488,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0.0125,
"maximumWordErrorRate": 0.35,
"speakerCount": 2,
"expectedSpeakerCount": 2,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"1": " The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]"
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. \n And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": 0.0125,
"maximumSpeakerWer": 0.35,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 10083.564041007776,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"linearQuantization": null,
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 21295.38541700458,
"inferenceMs": 21199.360792001244,
"firstChunkMs": 2372.6922500063665,
"audioSeconds": 35.644375,
"realTimeFactor": 0.5974402810262371,
"audioSecondsPerSecond": 1.681389139499386,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 13,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 1,
"totalMs": 31378.949458012357,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12466110464,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "cpu",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0.0125,
"maximumWordErrorRate": 0.35,
"speakerCount": 2,
"expectedSpeakerCount": 2,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"1": " The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]"
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. \n And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": 0.0125,
"maximumSpeakerWer": 0.35,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 2959.7039590007626,
"provider": "PyTorch CPU",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"cpu/torch.float32": 1176
},
"acceleration": "cpu",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"linearQuantization": null,
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 27090.874540997902,
"inferenceMs": 26994.56099900999,
"firstChunkMs": 2649.6446250239387,
"audioSeconds": 35.644375,
"realTimeFactor": 0.7600322502778601,
"audioSecondsPerSecond": 1.3204280299763804,
"activationPlacement": {
"decoderLayer": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "cpu",
"dtype": "torch.float32"
}
]
},
"chunkCount": 13,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": null,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "cpu",
"cpuThreads": 4,
"totalMs": 30050.578499998664,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "moderate",
"sampledPeakHelperRssBytes": 12074631168,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0.0125,
"maximumWordErrorRate": 0.35,
"speakerCount": 2,
"expectedSpeakerCount": 2,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"1": " The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]"
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. \n And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": 0.0125,
"maximumSpeakerWer": 0.35,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3558.3164999843575,
"provider": "Metal/MPS",
"precision": "fp16",
"parameterDtype": "torch.float16",
"placement": {
"mps:0/torch.float16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"linearQuantization": null,
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6867.568665998988,
"inferenceMs": 6774.114666011883,
"firstChunkMs": 1094.5539159874897,
"audioSeconds": 35.644375,
"realTimeFactor": 0.1926690723571107,
"audioSecondsPerSecond": 5.261849962304354,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float16"
}
]
},
"chunkCount": 13,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5650432000,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 10425.885165983345,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 6134284288,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "fp32",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0.0125,
"maximumWordErrorRate": 0.35,
"speakerCount": 2,
"expectedSpeakerCount": 2,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"1": " The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]"
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. \n And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": 0.0125,
"maximumSpeakerWer": 0.35,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3640.4949169955216,
"provider": "Metal/MPS",
"precision": "fp32",
"parameterDtype": "torch.float32",
"placement": {
"mps:0/torch.float32": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"linearQuantization": null,
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 8277.208959014388,
"inferenceMs": 8189.22300109989,
"firstChunkMs": 1258.1250420189463,
"audioSeconds": 35.644375,
"realTimeFactor": 0.2322164144837548,
"audioSecondsPerSecond": 4.352595477643315,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.float32"
}
]
},
"chunkCount": 13,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 11012898816,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 11917.70387600991,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 12130680832,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
},
{
"precision": "bf16",
"device": "mps",
"status": "pass",
"quality": {
"passed": true,
"wordErrorRate": 0.0125,
"maximumWordErrorRate": 0.35,
"speakerCount": 2,
"expectedSpeakerCount": 2,
"speakerContent": {
"0": " And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country.",
"1": " The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]"
},
"plainTranscript": "And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog. \n And so, my fellow Americans, ask not what your country can do for you, ask what you can do for your country. \n The quick brown fox jumps over the lazy dog. The quick brown fox jumps over the lazy dog.[Silence]",
"maximumConsecutiveRepeatedWords": 1,
"permutationInvariantSpeakerWer": 0.0125,
"maximumSpeakerWer": 0.35,
"scope": "Speaker-prefix native output; labels are not personal identities, no timestamps inferred"
},
"runtime": {
"engine": "vibevoice-asr",
"version": "1.0.0+16fb2cb",
"transformersVersion": "4.57.6",
"torchVersion": "2.10.0",
"loadMs": 3212.288541981252,
"provider": "Metal/MPS",
"precision": "bf16",
"parameterDtype": "torch.bfloat16",
"placement": {
"mps:0/torch.bfloat16": 1176
},
"acceleration": "partial",
"accelerationDetails": "Acoustic/semantic encoders/connectors, Qwen decoder and logits on selected device; WAV decode/resample/tokenization/text decoding CPU",
"checkpointLoading": {
"missing_keys": [],
"unexpected_keys": [],
"mismatched_keys": [],
"error_msgs": []
},
"linearQuantization": null,
"chunkFrames": 22,
"lookaheadFrames": 4,
"sampleRate": 24000,
"chunkSeconds": 2.933333333333333,
"lookaheadSeconds": 0.5333333333333333,
"attentionImplementation": "sdpa",
"streaming": "Model chunk text emitted incrementally from complete WAV input",
"durationMs": 6719.693749997532,
"inferenceMs": 6619.256458070595,
"firstChunkMs": 1047.2332909994293,
"audioSeconds": 35.644375,
"realTimeFactor": 0.18852045378822133,
"audioSecondsPerSecond": 5.384951501091974,
"activationPlacement": {
"decoderLayer": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"logits": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"acousticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
],
"semanticConnector": [
{
"device": "mps:0",
"dtype": "torch.bfloat16"
}
]
},
"chunkCount": 13,
"temperature": 0,
"maxNewTokensPerChunk": 256,
"implicitMpsFallback": false,
"driverAllocatedMemoryBytes": 5651038208,
"memoryMeasurementScope": "Post-generation Metal driver allocation, not peak VRAM",
"device": "mps",
"cpuThreads": 4,
"totalMs": 9931.982291978784,
"artifactRevision": "4262d23d8a539a6530cf64fbd0b1751ef9a30853",
"fallback": false,
"grade": "fast",
"sampledPeakHelperRssBytes": 768131072,
"rssScope": "200ms helper process RSS sampling; not peak VRAM or validated minimum"
}
}
]